tistou77 Posted October 25, 2018 Share Posted October 25, 2018 Hello It's normal that the score of Double-Precision Mandel is higher with GTX 1080 than with RTX 2080 ? Thanks Quote Link to comment Share on other sites More sharing options...
Fiery Posted October 26, 2018 Share Posted October 26, 2018 17 hours ago, tistou77 said: Hello It's normal that the score of Double-Precision Mandel is higher with GTX 1080 than with RTX 2080 ? Thanks There're a few compromises in the Turing uarch compared to Pascal/Volta that could explain the performance drop. We however had no chance to dig deeper into Turing just yet. Once we can get a test sample, we'll analyze the issue. There may not be room for further optimizations though (on our side), since our OpenCL benchmarks rely heavily on the OpenCL compiler, and the fractal benchmarks are quite simply "too simple" to leave room for any tweakings on our part. nVIDIA may find some tricks on their side that they can implement in their OpenCL compiler, but I'm not sure how much attention they have about OpenCL benchmarks and optimizing their compiler to better work with such benchmarks Quote Link to comment Share on other sites More sharing options...
tistou77 Posted October 26, 2018 Author Share Posted October 26, 2018 Ok thanks for the explanation Quote Link to comment Share on other sites More sharing options...
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.